© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36610
    Prev
    Next
    INDEX
    Explanations

    engorged member

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    r
    0.88
    V
    0.74
    H
    0.70
     Ancak
    0.68
    W
    0.68
    ")',
    0.66
     років
    0.66
     चुनावी
    0.66
     बेशक
    0.65
     忄
    0.65
    POSITIVE LOGITS
    ↵
    0.76
    8
    0.59
     Bé
    0.59
    ää
    0.58
    ë
    0.58
    ми
    0.56
    ène
    0.56
    <0xAF>
    0.55
    oting
    0.55
    uning
    0.55
    Activations Density 0.001%

    No Known Activations